Abstract 204P
Background
Although neoadjuvant chemoradiotherapy followed by surgery is the standard treatment for esophageal cancer patients, most patients are unable to achieve pathological complete response with neoadjuvant therapy, resulting in poor outcomes. The aim of this study is to develop a method for selecting patients who can achieve pathological complete response through pre-neoadjuvant therapy chest-enhanced CT scans.
Methods
Two hundreds and one patients with esophageal cancer were enrolled and divided into a training set and a testing set in a 7:3 ratio. Radiomics features of intra-tumoral and peritumoral images were extracted from preoperative chest-enhanced CT scans of these patients. The features were dimensionally reduced in two steps. The selected intra-tumoral and peritumoral features, including marginal (with a distance of 0-3mm from the tumor) and adjacent (with a distance of 3-6mm from the tumor) ROI, were used to build models with four machine learning classifiers, including Support Vector Machine, XG-Boost, Random Forest and Naive Bayes. Models with satisfied accuracy and stability levels were considered to perform well. Finally, the performance of these well-performing models on the testing set was displayed using ROC curves.
Results
Among the 16 models, the best-performing models were the integrated (intra-tumoral and peritumoral features)-XGBoost and integrated-random forest models, which had average ROC AUCs of 0.906 and 0.918, respectively, with relative standard deviations (RSDs) of 6.26 and 6.89 in the training set. In the testing set, the AUCs were 0.845 and 0.871, respectively. There was no significant difference in the ROC curves between the two models. Table: 204P
The performance of the selected models on the testing set
Model | AUC (95% CI) | Specificity | Sensitivity |
Integrated-XGBoost | 0.845 (0.764, 0.928) | 0.864 | 0.777 |
Original-XGBoost | 0.759 (0.660, 0.857) | 0.900 | 0.592 |
Integrated-Random Forest | 0.871 (0.796, 0.946) | 0.682 | 0.933 |
Original-Random Forest | 0.795 (0.703, 0.887) | 0.825 | 0.673 |
Adjacent-Random Forest | 0.769 (0.671, 0.868) | 0.886 | 0.533 |
Integrated-Support Vector Machine | 0.719 (0.613, 0.825) | 0.795 | 0.622 |
Conclusions
The addition of peritumoral radiomics features to the radiomics analysis may improve the predictive performance of pathological response for esophageal cancer patients to neoadjuvant chemoradiotherapy.
Clinical trial identification
Editorial acknowledgement
Legal entity responsible for the study
The authors.
Funding
Has not received any funding.
Disclosure
All authors have declared no conflicts of interest.
Resources from the same session
49P - Survival outcomes of HER2-positive breast cancer patients treated with neoadjuvant therapy at a single cancer centre in India
Presenter: Minit Shah
Session: Poster Display
Resources:
Abstract
50P - A nationwide retrospective cohort study of the response to neoadjuvant chemotherapy between HER-2 low and HER-2 negative non-metastatic breast cancer in Qatar: A real-world analysis
Presenter: Ahmed Kardousha
Session: Poster Display
Resources:
Abstract
51P - Four-year outcomes of hypofractionated postmastectomy radiation therapy of 39 Gy in 13 fractionations
Presenter: Sevinj Gahramanova
Session: Poster Display
Resources:
Abstract
52P - A comparative study to assess volumetric and dosimetric profile of heart and lung in patients undergoing left sided post mastectomy radiotherapy: Continuous positive airway pressure (CPAP) versus free breathing (FB) techniques
Presenter: Pritanjali Singh
Session: Poster Display
Resources:
Abstract
29P - HUWE1 inhibition has tumor suppressive effect in triple-negative breast cancer cell lines by modulating glycolytic and immune modulatory markers
Presenter: Shruti Kahol
Session: Poster Display
Resources:
Abstract
53P - Radiotherapy utilization rate for breast cancer in Indonesia: A call for empowering cancer care
Presenter: Donald Manuain
Session: Poster Display
Resources:
Abstract
58P - Safety and pharmacokinetics (PK) of vepdegestrant in Japanese patients with estrogen receptor (ER)+/human epidermal growth factor receptor 2 (HER2)- advanced breast cancer: Results from a Japanese phase I study
Presenter: Hiroji Iwata
Session: Poster Display
Resources:
Abstract
59P - Comprehensive genomic profiling (CGP) unravels druggable targets in breast carcinoma (BC): A single institutional experience
Presenter: Gautam Balaram
Session: Poster Display
Resources:
Abstract
60P - A study of gene alterations in Asian patients with late stage and recurrent breast cancer
Presenter: Po-Sheng Yang
Session: Poster Display
Resources:
Abstract
61P - Tumor cell-released autophagosomes (TRAPs) remodel the breast tumor microenvironment by inducing the formation of inflammatory cancer-associated fibroblasts (CAFs)
Presenter: Chengdong Wu
Session: Poster Display
Resources:
Abstract